{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:18:33Z","timestamp":1770063513861,"version":"3.49.0"},"reference-count":50,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Today, foundation models simulate humans\u2019 skills in translation, literature review, fact checking, fake-news detection, novel and poetry production. However, generative AI can also be applied to discourse analysis. This study instructed the Gemini 2.5 model to analyze multimodal political discourse. We selected some fragments from the Trump\u2013Zelensky debate held at the White House on 28 February 2025 and annotated each sentence, gesture, intonation, gaze, and facial expression in terms of LEP (Logos, Ethos, Pathos) analysis to assess when speakers, in words or body communication, rely on rational argumentation, stress their own merits or the opponents\u2019 demerits, or express and try to induce emotions in the audience. Through detailed prompts, we asked the Gemini 2.5 model to run the LEP analysis on the same fragments. Then, considering the human\u2019s and model\u2019s annotations in parallel, we proposed a metric to compare their respective analyses and measure discrepancies, finally tuning an optimized prompt for the model\u2019s best performance, which in some cases outperformed the human\u2019s analysis: an interesting application, since the LEP analysis highlights deep aspects of multimodal discourse but is highly time-consuming, while its automatic version allows us to interpret large chunks of speech in a fast but reliable way.<\/jats:p>","DOI":"10.3390\/info17020136","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T09:00:33Z","timestamp":1770022833000},"page":"136","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Ten Minutes That Shocked the World\u2014Teaching Generative AI to Analyze the Trump\u2013Zelensky Multimodal Debate"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4067-3424","authenticated-orcid":false,"given":"Isabella","family":"Poggi","sequence":"first","affiliation":[{"name":"Department of Philosophy, Communication and Performing Arts, Roma Tre University, 00146 Rome, Italy"}]},{"given":"Tommaso","family":"Scaramella","sequence":"additional","affiliation":[{"name":"Independent Researcher, 00100 Rome, Italy"}]},{"given":"Sissy","family":"Violini","sequence":"additional","affiliation":[{"name":"Independent Researcher, 00100 Rome, Italy"}]},{"given":"Simona","family":"Careri","sequence":"additional","affiliation":[{"name":"Independent Researcher, 00100 Rome, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2173-1366","authenticated-orcid":false,"given":"Maria D\u00e9sir\u00e9e","family":"Epure","sequence":"additional","affiliation":[{"name":"Department of Education, Roma Tre University, 00185 Rome, Italy"},{"name":"Department of Education, Cultural Heritage and Tourism, University of Macerata, 62100 Macerata, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9637-4771","authenticated-orcid":false,"given":"Daniele","family":"Dragoni","sequence":"additional","affiliation":[{"name":"Department of Education, Roma Tre University, 00185 Rome, Italy"},{"name":"Department of Education, Cultural Heritage and Tourism, University of Macerata, 62100 Macerata, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103599","DOI":"10.1016\/j.inffus.2025.103599","article-title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","volume":"126","author":"Sapkota","year":"2026","journal-title":"Inf. Fusion"},{"key":"ref_2","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_3","unstructured":"Gemini Team (2023). Gemini: A Family of Highly Capable Multimodal Models, Gemini Team."},{"key":"ref_4","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling Laws for Neural Language Models. arXiv."},{"key":"ref_5","unstructured":"Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., de Las Casas, D., Hendricks, L.A., Welbl, J., and Clark, A. (2022). Training Compute-Optimal Large Language Models. arXiv."},{"key":"ref_6","unstructured":"Gemini Team (2024). Google Gemini 1.5: Unlocking Multimodal Understanding across Millions of Tokens of Context. arXiv."},{"key":"ref_7","unstructured":"Gemini Team (2025). Google Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context. arXiv."},{"key":"ref_8","unstructured":"(2025, December 16). Anthropic Introducing the Model Context Protocol. Available online: https:\/\/www.anthropic.com\/news\/model-context-protocol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Qu, C., Dai, S., Wei, X., Cai, H., Wang, S., Yin, D., Xu, J., and Wen, J.-R. (2024). Tool Learning with Large Language Models: A Survey. arXiv.","DOI":"10.1007\/s11704-024-40678-2"},{"key":"ref_10","unstructured":"Yehudai, A., Eden, L., Li, A., Uziel, G., Zhao, Y., Bar-Haim, R., Cohan, A., and Shmueli-Scheuer, M. (2025). Survey on Evaluation of LLM-Based Agents. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Garg, R., Han, J., Cheng, Y., Fang, Z., and Swiecki, Z. (2024, January 18\u201322). Automated Discourse Analysis via Generative Artificial Intelligence. Proceedings of the 14th Learning Analytics and Knowledge Conference, Kyoto, Japan.","DOI":"10.1145\/3636555.3636879"},{"key":"ref_12","unstructured":"Herring, S.C. (2026, January 26). D\u00e9bats Sur Le D\u00e9bat\u2014Susan Herring\u2014Is Generative AI the Future of Qualitative Discourse Analysis?, Available online: https:\/\/www.youtube.com\/watch?v=s2XZQhaaCMg."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1177\/0261927X09351676","article-title":"The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods","volume":"29","author":"Tausczik","year":"2010","journal-title":"J. Lang. Soc. Psychol."},{"key":"ref_14","unstructured":"Walker, J., Koutsiana, E., Massey, J., Thuermer, G., and Simperl, E. (2023). Prompting Datasets: Data Discovery with Conversational Agents. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"231053","DOI":"10.1098\/rsos.231053","article-title":"Using ChatGPT for Human\u2013Computer Interaction Research: A Primer","volume":"10","author":"Tabone","year":"2023","journal-title":"R. Soc. Open Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1177\/08944393231220483","article-title":"Performing an Inductive Thematic Analysis of Semi-Structured Interviews with a Large Language Model: An Exploration and Provocation on the Limits of the Approach","volume":"42","year":"2024","journal-title":"Soc. Sci. Comput. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"16094069231201504","DOI":"10.1177\/16094069231201504","article-title":"Exploring the Use of AI in Qualitative Analysis: A Comparative Study of Guaranteed Income Data","volume":"22","author":"Hamilton","year":"2023","journal-title":"Int. J. Qual. Methods"},{"key":"ref_18","unstructured":"Chew, R., Bollenbacher, J., Wenger, M., Speer, J., and Kim, A. (2023). LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4945","DOI":"10.1007\/s11135-025-02165-z","article-title":"ChatGPT in Thematic Analysis: Can AI Become a Research Assistant in Qualitative Research?","volume":"59","year":"2025","journal-title":"Qual. Quant."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"T\u00f6rnberg, P. (2023). How to Use Large Language Models for Text Analysis. arXiv.","DOI":"10.4135\/9781529683707"},{"key":"ref_21","unstructured":"Chiu, K.L., Collins, A., and Alexander, R. (2021). Detecting Hate Speech with GPT-3. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Huang, F., Kwak, H., and An, J. (2023). Is ChatGPT Better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech. arXiv.","DOI":"10.1145\/3543873.3587368"},{"key":"ref_23","unstructured":"Fan, Y., Jiang, F., Li, P., and Li, H. (2023). Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Labruna, T., Brenna, S., Zaninello, A., and Magnini, B. (2023). Unraveling ChatGPT: A Critical Analysis of AI-Generated Goal-Oriented Dialogues and Annotations, Springer Nature.","DOI":"10.1007\/978-3-031-47546-7_11"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Siiman, L.A., Rannastu-Avalos, M., P\u00f6ys\u00e4-Tarhonen, J., H\u00e4kkinen, P., Pedaste, M., Huang, Y.-M., and Rocha, T. (2023). Opportunities and Challenges for AI-Assisted Qualitative Data Analysis: An Example from Collaborative Problem-Solving Discourse Data, Springer.","DOI":"10.1007\/978-3-031-40113-8_9"},{"key":"ref_26","first-page":"5","article-title":"Further Explorations on the Use of Large Language Models. Open-Ended Prompts, Better Terminologies and Thematic Maps","volume":"25","year":"2024","journal-title":"Forum Qual. Sozialforschung\/Forum Qual. Soc. Res."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1080\/17405904.2024.2373733","article-title":"The Rise of Large Language Models: Challenges for Critical Discourse Studies","volume":"22","author":"Gillings","year":"2025","journal-title":"Crit. Discourse Stud."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Barab, S.A., Kling, R., and Gray, J.H. (2004). Computer-Mediated Discourse Analysis: An Approach to Researching Online Behavior. Designing for Virtual Communities in the Service of Learning, Cambridge University Press.","DOI":"10.1017\/CBO9780511805080"},{"key":"ref_29","unstructured":"Bucholtz, M., Liang, A.C., and Sutton, L. (1994). Politeness in Computer Culture: Why Women Thank and Men Flame. Cultural Performances: Proceedings of the Third Berkeley Women and Language Conference, Berkeley Women and Language Group."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"100931","DOI":"10.1016\/j.dcm.2025.100931","article-title":"Methodological Synergies in the Study of Digital Discourse: A Critical Reflection","volume":"66","author":"Herring","year":"2025","journal-title":"Discourse Context Media"},{"key":"ref_31","unstructured":"Parisi, D., and Castelfranchi, C. (1976). Discourse as a Hierarchy of Goals, Centro Internazionale di Semiotica e Linguistica (Universit\u00e0 di Urbino). Working Papers."},{"key":"ref_32","unstructured":"Conte, R., and Castelfranchi, C. (1995). Cognitive and Social Action, Garland Science."},{"key":"ref_33","unstructured":"Poggi, I. (2007). Mind, Hands, Face and Body. A Goal and Belief View of Multimodal Communication, Weidler."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Poggi, I. (2024). The Language of Gaze. Eyes That Talk, Routledge.","DOI":"10.4324\/9781032678344"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Poggi, I., and D\u2019Errico, F. (2022). Social Influence, Power, and Multimodal Communication, Routledge.","DOI":"10.4324\/9781003029274"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1075\/pc.13.2.04pog","article-title":"The Goals of Persuasion","volume":"13","author":"Poggi","year":"2005","journal-title":"Pragmat. Cogn."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Castelfranchi, C., and Falcone, R. (2010). Trust Theory: A Socio-Cognitive and Computational Model, John Wiley & Sons.","DOI":"10.1002\/9780470519851"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Macagno, F., and Walton, D. (2014). Emotive Language in Argumentation, Cambridge University Press.","DOI":"10.1017\/CBO9781139565776"},{"key":"ref_39","first-page":"13","article-title":"Sfumature del razionale. La comunicazione politica emozionale nell\u2019ecosistema ibrido dei media","volume":"19","author":"Cepernich","year":"2018","journal-title":"Comun. Politica"},{"key":"ref_40","first-page":"1114","article-title":"Persuasion Through Emotion? An Experimental Test of the Emotion-Eliciting Nature of Populist Communication","volume":"12","author":"Wirz","year":"2018","journal-title":"Int. J. Commun."},{"key":"ref_41","unstructured":"Novelli, E. (2023). Stili Di Discorso e Orientamento Politico. Populismo, Sovranismo e Strutture Persuasive. Il Ritorno Della Nazione: Linguaggi e Culture Politiche in Europa e Nelle Americhe, Carocci editore. Available online: https:\/\/independent.academia.edu\/PoggiIsabella."},{"key":"ref_42","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020, January 6\u201312). Language Models Are Few-Shot Learners. Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_43","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E.H., Le, Q.V., and Zhou, D. (December, January 28). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_44","unstructured":"Zhang, Y., Yuan, Y., and Yao, A.C.-C. (2023). Meta Prompting for AI Systems. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Pryzant, R., Iter, D., Li, J., Lee, Y., Zhu, C., and Zeng, M. (2023, January 6\u201310). Automatic Prompt Optimization with \u201cGradient Descent\u201d and Beam Search. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.494"},{"key":"ref_46","unstructured":"Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., and Steinhardt, J. (2021). Measuring Massive Multitask Language Understanding. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Yue, X., Ni, Y., Zhang, K., Zheng, T., Liu, R., Zhang, G., Stevens, S., Jiang, D., Ren, W., and Sun, Y. (2024, January 16\u201322). MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref_48","unstructured":"Lu, P., Bansal, H., Xia, T., Liu, J., Li, C., Hajishirzi, H., Cheng, H., Chang, K.-W., Galley, M., and Gao, J. (2024). MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Sabour, S., Liu, S., Zhang, Z., Liu, J., Zhou, J., Sunaryo, A., Lee, T., Mihalcea, R., and Huang, M. (2024). EmoBench: Evaluating the Emotional Intelligence of Large Language Models, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.acl-long.326"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1093\/ej\/ueab104","article-title":"Emotion and Reason in Political Language","volume":"132","author":"Gennaro","year":"2022","journal-title":"Econ. J."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/136\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T09:20:51Z","timestamp":1770024051000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":50,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["info17020136"],"URL":"https:\/\/doi.org\/10.3390\/info17020136","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]}}}